explainability · GitHub Topics

shap / shap

#计算机科学#A game theoretic approach to explain the output of any machine learning model.

翻译 - 一种解释任何机器学习模型输出的博弈论方法。

interpretability 机器学习深度学习 gradient-boosting shap shapley explainability

Jupyter Notebook 23.53 k

4 天前

EthicalML / awesome-production-machine-learning

#Awesome#A curated list of awesome open source libraries to deploy, monitor, version and scale your machine learning

翻译 - 精选的优秀开源库列表，用于部署，监视，版本化和扩展您的机器学习

机器学习 mlops interpretability explainability responsible-ai 深度学习 machine-learning-operations ml-ops ml-operations privacy-preserving privacy-preserving-machine-learning data-mining production-machine-learning Awesome Lists

18.18 k

1 天前

interpretml / interpret

#计算机科学#Fit interpretable models. Explain blackbox machine learning.

翻译 - 拟合可解释的模型。说明黑匣子机器学习。

机器学习 interpretability gradient-boosting blackbox scikit-learn xai interpretml interpretable-machine-learning interpretable-ai transparency interpretable-ml explainable-ml explainability bias 人工智能 explainable-ai differential-privacy

C++ 6.42 k

13 小时前

MAIF / shapash

#计算机科学#🔅 Shapash: User-friendly Explainability and Interpretability to Develop Reliable and Transparent Machine Learning Models

翻译 - Shapash使机器学习模型透明且每个人都可以理解

Python 机器学习 explainability explainable-ml transparency ethical-artificial-intelligence shap lime interpretability

Jupyter Notebook 2.85 k

1 个月前

hila-chefer / Transformer-Explainability

#计算机科学#[CVPR 2021] Official PyTorch implementation for Transformer Interpretability Beyond Attention Visualization, a novel method to visualize classifications by Transformer based networks.

深度学习 vision-transformer bert-model bert explainability vit cvpr2021

Jupyter Notebook 1.85 k

1 年前

microsoft / responsible-ai-toolbox

#计算机科学#Responsible AI Toolbox is a suite of tools providing model and data exploration and assessment user interfaces and libraries that enable a better understanding of AI systems. These interfaces and libr...

ui responsible-ai 数据科学 fairness fairness-ml fairness-ai explainable-ai explainable-ml explainability 机器学习可视化 widgets widget Jupyter Notebook 数据分析数据可视化 interpretability

TypeScript 1.48 k

1 个月前

EthicalML / xai

#计算机科学#XAI - An eXplainability toolbox for machine learning

explainability xai 机器学习人工智能 bias explainable-ai explainable-ml interpretability xai-library evaluation upsampling feature-importance

Python 1.16 k

3 年前

hila-chefer / Transformer-MM-Explainability

[ICCV 2021- Oral] Official PyTorch implementation for Generic Attention-model Explainability for Interpreting Bi-Modal and Encoder-Decoder Transformers, a novel method to visualize any Transformer-bas...

transformers transformer vqa detr 可视化 explainability explainable-ai interpretability clip

Jupyter Notebook 835

2 年前

h1st-ai / h1st

#时序数据库#Power Tools for AI Engineers With Deadlines

翻译 - H1st AI解决了工业AI的关键“冷启动”问题：对人类专业知识进行编码以增加数据的缺乏，同时构建向机器学习未来的平稳过渡。此问题已导致大多数工业AI项目失败。

数据科学 explainability home-automation time-series collaboration Cybersecurity cold-start autonomous-vehicles automl avionics human-in-the-loop industrial-iot Hacktoberfest

Jupyter Notebook 797

2 年前

MisaOgura / flashtorch

#计算机科学#Visualization toolkit for neural networks in PyTorch! Demo -->

PyTorch neural-networks cnn interpretability 机器学习深度学习可视化 explainability

HTML 739

1 年前

flyingdoog / awesome-graph-explainability-papers

#计算机科学#Papers about explainability of GNNs

机器学习深度学习 graph-neural-networks xai explainable-ai explainability

700

6 天前

alvinwan / neural-backed-decision-trees

Making decision trees competitive with neural networks on CIFAR10, CIFAR100, TinyImagenet200, Imagenet

decision-trees neural-networks image-classification explainability cifar10 cifar100 interpretability imagenet pretrained-weights pretrained-models PyTorch

Python 616

2 年前

mmschlk / shapiq

#计算机科学#Shapley Interactions and Shapley Values for Machine Learning

Python explainability interpretability 机器学习 shap shapley

Python 467

11 小时前

explainX / explainx

#计算机科学#Explainable AI framework for data scientists. Explain & debug any blackbox machine learning model with a single line of code. We are looking for co-authors to take this project forward. Reach out @ ms...